Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4566 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.9664. Min Act: -0.1700
Data Index: 5386332 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.7789. Min Act: -0.1700
Data Index: 3413572 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.6851. Min Act: -0.1700
Data Index: 6384450 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.6539. Min Act: -0.1700
Data Index: 8281046 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.5601. Min Act: -0.1700
Data Index: 5134801 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.4976. Min Act: -0.1700
Data Index: 533214 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.4976. Min Act: -0.1700
Data Index: 4788093 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.4664. Min Act: -0.1700
Data Index: 1146755 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.4351. Min Act: -0.1700
Data Index: 5651039 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.4039. Min Act: -0.1700
Data Index: 5631336 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.3414. Min Act: -0.1700
Data Index: 7974178 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.3101. Min Act: -0.1700
Data Index: 4310074 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.3101. Min Act: -0.1700
Data Index: 7269571 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.2789. Min Act: -0.1700
Data Index: 6504539 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.2476. Min Act: -0.1700
Data Index: 6716481 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.2476. Min Act: -0.1700
Data Index: 974184 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.2476. Min Act: -0.1700
Data Index: 1253610 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.2476. Min Act: -0.1700
Data Index: 7518640 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.2164. Min Act: -0.1700
Data Index: 4517347 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9664. Min Range: -7.9664
Max Act: 7.2164. Min Act: -0.1700
Data Index: 4271347 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19